IEEE Transactions on Pattern Analysis and Machine Intelligence
Machine Learning - Special issue on learning with probabilistic representations
Finite-time Analysis of the Multiarmed Bandit Problem
Machine Learning
Learning Bayesian network classifiers by maximizing conditional likelihood
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Discriminative parameter learning for Bayesian networks
Proceedings of the 25th international conference on Machine learning
Discriminative Learning of Bayesian Networks via Factorized Conditional Log-Likelihood
The Journal of Machine Learning Research
Bandit based monte-carlo planning
ECML'06 Proceedings of the 17th European conference on Machine Learning
Maximum Margin Bayesian Network Classifiers
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
In this work, we tackle the problem of structure learning for Bayesian network classifiers (BNC). Searching for an appropriate structure is a challenging task since the number of possible structures grows exponentially with the number of attributes. We formulate this search problem as a large Markov Decision Process (MDP). This allows us to tackle the problem using sequential decision making methods. Furthermore, we devise a Monte Carlo tree search algorithm to find a tractable solution for the MDP. The use of bandit-based action selection strategy enables us to have a systematic way of guiding the search, making the search in the large space of unrestricted structures tractable. The results of classification on different datasets show that the use of this method can significantly boost the performance of structure learning for BNCs.